Skip to main content
Fig. 1 | BMC Medical Research Methodology

Fig. 1

From: A comparison of multiple imputation methods for handling missing values in longitudinal data in the presence of a time-varying covariate with a non-linear association with time: a simulation study

Fig. 1

a) Variable dependencies of simulated time-independent variables; m_age, maternal age at child birth; m_education, maternal education; m_smoking, maternal smoking; sex, study child’s sex; birthweight, study child’s birth weight; b) Causal diagram for the association between sleep problems and BMI for age z-scores. For the ease of presentation all time-independent variables are presented using a single node excluding maternal smoking; scage1-scage5, study child’s age at waves 1 to 5; bmiz1-bmiz5, study child’s BMI for age z-scores at waves 1 to 5; sleep_prob1-sleep_prob5, study child’s sleep problems at waves 1 to 5; c) Causal diagram for MAR missingness. R is an indicator variable of missingness where BMI for age z-scores were assigned to missing if R = 1. Only variables required to model the MAR missingness are shown in the figure

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us